© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7282
    Prev
    Next
    INDEX
    Explanations

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    审美
    0.29
    容
    0.26
    OTOS
    0.25
     pét
    0.25
    毖
    0.25
    rivia
    0.24
    largest
    0.23
    Clause
    0.23
    Virt
    0.23
    Dado
    0.23
    POSITIVE LOGITS
    輾
    0.29
    ასი
    0.28
     ನ್ಯಾಯ
    0.27
    ╞
    0.27
    aadhar
    0.26
     Technology
    0.26
     Tanj
    0.26
     cy
    0.25
     slated
    0.25
     Jelly
    0.25
    Activations Density 0.000%

    No Known Activations